Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: [QA] Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Description:
The paper identifies "underthinking" in LLMs, where frequent thought switching hampers reasoning depth. It proposes a new strategy to improve accuracy in complex tasks without model fine-tuning.
https://arxiv.org/abs//2501.18585
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers